Automatic Classification of Magnetic Chirality of Solar Filaments from H-Alpha Observations
In this study, we classify the magnetic chirality of solar filaments from H-Alpha observations using state-of-the-art image classification models. We establish the first reproducible baseline for solar filament chirality classification on the MAGFiLO dataset. The MAGFiLO dataset contains over 10,000 manually-annotated filaments from GONG H-Alpha observations, making it the largest dataset for filament detection and classification to date. Prior studies relied on much smaller datasets, which limited their generalizability and comparability. We fine-tuned several pre-trained, image classification architectures, including ResNet, WideResNet, ResNeXt, and ConvNeXt, and also applied data augmentation and per-class loss weights to optimize the models. Our best model, ConvNeXtBase, achieves a per-class accuracy of 0.69 for left chirality filaments and $0.73$ for right chirality filaments.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ClassificationData AugmentationSimilar Papers 제목 키워드 기반
Machine learning for reconstruction of polarity inversion lines from solar filaments
Solar filaments are well-known tracers of polarity inversion lines that separate two opposite magnetic polarities on the solar photosphere. Because observations of filaments began long before the systematic observations …
Super-ResolutionChirality-Induced Magnetization of Magnetite by an RNA Precursor
Life is homochiral and homochirality is a fundamental feature of living systems on Earth. While the exact mechanism that led to homochirality is still not fully understood, any realistic scenario on the origins of life n…
Variational autoencoders understand knot topology
Supervised machine learning (ML) methods are emerging as valid alternatives to standard mathematical methods for identifying knots in long, collapsed polymers. Here, we introduce a hybrid supervised/unsupervised ML appro…
DecodervalidSolar Filaments Detection using Active Contours Without Edges
In this article, an active contours without edges (ACWE)-based algorithm has been proposed for the detection of solar filaments in H-alpha full-disk solar images. The overall algorithm consists of three main steps of ima…
Image SegmentationObjectobject-detectionObject Detection+1EdgeAttNet: Towards Barb-Aware Filament Segmentation
Accurate segmentation of solar filaments in H-alpha observations is critical for determining filament chirality, a key factor in the behavior of Coronal Mass Ejections (CMEs). However, existing methods often fail to capt…